arXiv Artificial Intelligence

DDGAD: Disagreement-Driven Graph Anomaly Detection via Adapt-Then-Combine

2 hours ago 23.09.2026 07:00 👁 1 views
DDGAD: Disagreement-Driven Graph Anomaly Detection via Adapt-Then-Combine

Quick summary

arXiv:2605.26446v3 Announce Type: replace-cross Abstract: Graph anomaly detection (GAD) commonly relies on message passing to jointly encode node attributes and neighborhood context. However, once the two are mixed, an abnormal post-encoding state may reflect either an intrinsic node deviation or incompatible contextual influence, making its source ambiguous. We propose Disagreement-Driven Graph Anomaly Detection (DDGAD), which treats persistent incompatibility between node-wise and contextual estimates as anomaly evidence. Inspired by Adapt-Then-Combine (ATC), DDGAD reverses its consensus obj

Key takeaways

  • arXiv:2605.26446v3 Announce Type: replace-cross Abstract: Graph anomaly detection (GAD) commonly relies on message passing to jointly encode node attributes and neighborhood context.
  • However, once the two are mixed, an abnormal post-encoding state may reflect either an intrinsic node deviation or incompatible contextual influence, making its source ambiguous.
  • We propose Disagreement-Driven Graph Anomaly Detection (DDGAD), which treats persistent incompatibility between node-wise and contextual estimates as anomaly evidence.

Why it matters

“DDGAD: Disagreement-Driven Graph Anomaly Detection via Adapt-Then-Combine” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗